Skip to main content

How to Get Started with Video Translation

Learn how to translate your content into any language with HeyGen's Video Translation tool.

Written by Avi
Updated today

HeyGen's video translation tool makes it easy to translate videos into multiple languages, expanding your content's global reach. With customizable options and user-friendly features, it's a powerful way to break language barriers and connect with a wider audience effortlessly.


Getting Started

To generate a translation, start by clicking 'Translate' on the left side bar. From this window, you can either upload a file from your device or paste a YouTube link/ Google Drive link / Viemo link.

Before you start: choose Audio Dubbing or Video Dubbing

Before translating your video, you can choose between Audio Dubbing and Video Dubbing.

Audio Dubbing translates the audio only. It does not include lip sync, and the original speaker’s voice is still used. Audio Dubbing is unlimited on paid plans and does not use credits.

Video Dubbing translates the audio including lip sync. This option uses credits- more on that below.

Speed vs. Precision mode

When using Video Dubbing, you can choose between Speed and Precision mode.

  • Speed mode costs 5 credits per minute

  • Precision mode costs 10 credits per minute

Precision mode is designed for higher translation accuracy, but it costs double the credits of Speed mode.

If you want to improve translation quality without using Precision mode, there are other tools that can help:

  • Brand Glossary- useful for keeping brand names, product terms, and specific wording consistent. See more here.

  • Proofread ( also called "Review & Edit") lets you review and edit each word in the translated script before generating the final result. Available on Pro, Business, and Enterprise plans. See more here.

  • Add Transcription (SRT/ASS) -


Choose Your Translation Advance Settings

On the translation page, you’ll find a range of Advanced options that let you fully customize your translated video. Here’s a quick overview of each feature:

  • Source Language: Automatically detect the language of your video or choose it manually.

  • Target Language: Select the language for translation, with an option to choose a preferred locale for regional accents.
    You can translate the same video into multiple languages at once, with a maximum of 10 languages per job.

    We recommend doing this only after you’re confident in the translation quality and complexity level of language in your video.

    This can help you avoid spending credits on translations that may need to be revised.

  • Brand Glossary: Maintain consistent pronunciation and translation of key terms, such as company or product names. (Click here to learn more about Brand Glossary.)

  • Enable Dynamic Duration: Automatically adjust segment durations to improve translation and audio quality creating a more natural-sounding speech.
    Note: This may affect the total length of your video.

  • Create a Collection: Combine all multilingual translations into one organized collection on your main page.

  • Remove Background Sound: Eliminate background noise or ambient sounds from your video.

  • Output to Original Video Specs: Retain your video’s original resolution (e.g. 720p, 1080p, 4K). This is available for Pro/Business/Enterprise plans only.

  • Enable Captions: Add translated captions, or subtitles, to the video for accessibility and clarity.

  • Enhance Voice: Boost volume and improve clarity for a studio-quality sound

Note: though this may slightly alter the original tone of the audio.

Once you've covered everything, just press Translate and your video will be ready soon!

🛎️ Pro tip- the default accent for languages is usually the most common one. For example the default for English would be American accent. 🛎️

🛎️ Note: Enterprise users can choose local voice files to help create a more accurate voice clone for this specific video.


Video Translate File Requirements

When using HeyGen's Video Translation tool, your source video must meet specific requirements for file size, type, and input language. These details can be found under the "Requirements" info button within the tool.

We're continuously adding more supported languages based on user feedback. Currently supported languages include:

Input Languages:
Arabic, Bengali, Catalan, Danish, Dutch, English, Filipino, Finnish, French, German, Hebrew, Hindi, Italian, Japanese, Korean, Mandarin, Malayalam, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian, Urdu, Vietnamese.

Output Languages:
Arabic, Bengali, Bulgarian, Croatian, Czech, Danish, Dutch, English (American Accent or Your Accent), Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Malayalam, Mandarin, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, Ukrainian.

Please note that the above list may not be up to date, as new languages are added frequently!

Video files uploaded locally or linked from YouTube/Google Drive must meet these criteria:

  • File type: mp4, mov, webm

  • File size: up to 5GB

  • File length: 2 seconds to 10 hours (depending on your plan max duration limit)

  • Google Drive Link: file must be shared with "anyone with the link" access

  • Youtube Link: Make sure you're using the full URL address and not a shorten one.

  • Vimeo Link: Make sure you're using the full URL address and not a shorten one.


Translation Best Practices

Follow these guidelines to enhance the quality of your translation output.

Camera Angle
Ensure speakers face the camera directly or are at no more than a 45-degree angle.

Proximity to Camera
Keep speakers within 10 feet of the camera for clearer audio and better capture of facial expressions.

Single Speaker
Make sure only one person speaks at a time to improve lip sync accuracy.

Shot Composition
Use close-up shots and minimize camera cuts for smoother results.

Background Noise
Reduce background noise as much as possible to enhance audio quality.


Sharing + Downloading Your Translated Video

Once your video is created, click into the project to share your work. From there, you can download the video or share the video link directly. You can also generate and download captions, and export the ASS file to save locally on your device.


Translation Limits

All paid plans include Different amounts of Premium Credits which can be used for lip-sync translation.

Your Premium Credits balance on your account page= your Video Translation capacity

Examples by plan:

  • Creator: 200 credits → 40 min VT

  • Pro: 2000 credits → 400 min VT

  • Business: 1000 credits → 200 min VT

We also have unlimited Audio-Dubbing allowed with all paid plans, which means you can translate as many videos and minutes as you like if you choose Audio-only ( no lipsync) option. This option translates the Audio / Voice tracks, without changing the lipsync of the characters in the video, which is what we call Audio-Dubbing.

If you need more video-translations than your plan's Premium Credits allow, you can always purchase Premium Credits pack Add-on, which are $15 for 300 Premium Credits = 60 minutes of Video Translation.


Frequently Asked Questions (FAQ)

What are the video specs / requirements for downloading in the Translation tool?
Free users can export videos in up to 720p, Creator users in up to 1080p, and Pro/Business/Enterprise can export in 4K if the original video specs are of the same resolution.

I have enough Premium Credits to translate more than 30 minutes, why did I just hit a 30 minute limit?

You’re seeing the 30-minute limit because Creator and Pro plans cap the max duration per video at 30 minutes. Premium Credits only add more total translation minutes in your pool. They don’t change the per-video cap. You can translate longer content by splitting the video into parts under 30 minutes each or by upgrading to business plan for 60 minutes limit or to enterprise plans for no duration limit.

Why did my translation fail?

Video translation can fail due to several factors, including improper speaker positioning, too many visible speakers, frequent camera cuts, or background noise. Follow the steps outlined in the 'Translation Best Practices' section above to ensure the best possible output.

My translation failed due to moderation. What does that mean and what can I do?

If your video failed due to moderation, you can submit it for manual approval by emailing [email protected] or using the chat feature. Please include the video ID so our moderation specialist can review it and get back to you as quickly as possible.

Why are all my translations going into a folder when I generate multiple at once?

When you generate multiple translations at once using batch mode (translating a single video into many languages), HeyGen automatically creates a subfolder to store those videos. This is expected behavior and is designed to help keep your main Projects view clean and organized.

If you only generate one video at a time, it will appear directly in your main Projects folder. But for batch workflows, folders are the default for better structure.

My translation is inaccurate - what can I do?

AI translation, while advanced, cannot guarantee 100% satisfactory results. It's constantly learning and improving, but there can still be occasional mistranslations. For users who require higher translation accuracy, HeyGen offers Script Proofread (also called Review & Edit) for Pro, Business and Enterprise plans. This allows you to adjust the translation for more accuracy before finalizing.

Why is the lip-sync off or not accurate?

There are several factors that can affect lipsyncing quality. Follow the steps outlined in the 'Translation Best Practices' section above to ensure the best possible output.

In my video there is text on the screen, and it did not translate, why?

In the Video Translation feature, the translation is done on the speaking voices including lipsync of the speakers, and not on elements showing on the screen like signs or text boxes. For on-screen translation you can create a draft of a new video in our Studio and that version can be translated to multiple languages, including elements on the screen that were inserted using Studio.

Can I use API to translate instead?

Yes, you can translate videos using our API instead of directly through the HeyGen platform. The HeyGen API allows developers to programmatically generate videos, create and customize avatars, and access a range of other features that may be available on the platform.

This option is ideal for those who prefer a more flexible, hands-on approach to integrating HeyGen’s video and avatar capabilities within their own systems or applications. The API provides the tools to create custom workflows, automate video production, and incorporate HeyGen's technology into broader projects, allowing you to create videos without needing to use the HeyGen app interface directly.

For more details on API capabilities and pricing, refer to our HeyGen API Plans article.

Did this answer your question?